Merge pull request #240 from zandrey/5.4-2.2.x-imx

[EOL]: Update 5.4-2.2.x-imx to v5.4.94

Documentation/admin-guide/device-mapper/dm-integrity.rst

@@ -177,6 +177,12 @@ bitmap_flush_interval:number
 	The bitmap flush interval in milliseconds. The metadata buffers
 	are synchronized when this interval expires.
 
+legacy_recalculate
+	Allow recalculating of volumes with HMAC keys. This is disabled by
+	default for security reasons - an attacker could modify the volume,
+	set recalc_sector to zero, and the kernel would not detect the
+	modification.
+
 
 The journal mode (D/J), buffer_sectors, journal_watermark, commit_time can
 be changed when reloading the target (load an inactive table and swap the

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 4
-SUBLEVEL = 93
+SUBLEVEL = 94
 EXTRAVERSION =
 NAME = Kleptomaniac Octopus
 

arch/arm64/include/asm/memory.h

@@ -178,7 +178,6 @@ extern u64			vabits_actual;
 #include <linux/bitops.h>
 #include <linux/mmdebug.h>
 
-extern s64			physvirt_offset;
 extern s64			memstart_addr;
 /* PHYS_OFFSET - the physical address of the start of memory. */
 #define PHYS_OFFSET		({ VM_BUG_ON(memstart_addr & 1); memstart_addr; })
@@ -254,7 +253,7 @@ static inline const void *__tag_set(const void *addr, u8 tag)
  */
 #define __is_lm_address(addr)	(!(((u64)addr) & BIT(vabits_actual - 1)))
 
-#define __lm_to_phys(addr)	(((addr) + physvirt_offset))
+#define __lm_to_phys(addr)	(((addr) & ~PAGE_OFFSET) + PHYS_OFFSET)
 #define __kimg_to_phys(addr)	((addr) - kimage_voffset)
 
 #define __virt_to_phys_nodebug(x) ({					\
@@ -272,7 +271,7 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x);
 #define __phys_addr_symbol(x)	__pa_symbol_nodebug(x)
 #endif /* CONFIG_DEBUG_VIRTUAL */
 
-#define __phys_to_virt(x)	((unsigned long)((x) - physvirt_offset))
+#define __phys_to_virt(x)	((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET)
 #define __phys_to_kimg(x)	((unsigned long)((x) + kimage_voffset))
 
 /*

arch/arm64/include/asm/pgtable.h

@@ -23,6 +23,8 @@
 #define VMALLOC_START		(MODULES_END)
 #define VMALLOC_END		(- PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
 
+#define vmemmap			((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT))
+
 #define FIRST_USER_ADDRESS	0UL
 
 #ifndef __ASSEMBLY__
@@ -33,8 +35,6 @@
 #include <linux/mm_types.h>
 #include <linux/sched.h>
 
-extern struct page *vmemmap;
-
 extern void __pte_error(const char *file, int line, unsigned long val);
 extern void __pmd_error(const char *file, int line, unsigned long val);
 extern void __pud_error(const char *file, int line, unsigned long val);

arch/arm64/mm/init.c

@@ -50,12 +50,6 @@
 s64 memstart_addr __ro_after_init = -1;
 EXPORT_SYMBOL(memstart_addr);
 
-s64 physvirt_offset __ro_after_init;
-EXPORT_SYMBOL(physvirt_offset);
-
-struct page *vmemmap __ro_after_init;
-EXPORT_SYMBOL(vmemmap);
-
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
@@ -321,20 +315,6 @@ void __init arm64_memblock_init(void)
 	memstart_addr = round_down(memblock_start_of_DRAM(),
 				   ARM64_MEMSTART_ALIGN);
 
-	physvirt_offset = PHYS_OFFSET - PAGE_OFFSET;
-
-	vmemmap = ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT));
-
-	/*
-	 * If we are running with a 52-bit kernel VA config on a system that
-	 * does not support it, we have to offset our vmemmap and physvirt_offset
-	 * s.t. we avoid the 52-bit portion of the direct linear map
-	 */
-	if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) {
-		vmemmap += (_PAGE_OFFSET(48) - _PAGE_OFFSET(52)) >> PAGE_SHIFT;
-		physvirt_offset = PHYS_OFFSET - _PAGE_OFFSET(48);
-	}
-
 	/*
 	 * Remove the memory that we will not be able to cover with the
 	 * linear mapping. Take care not to clip the kernel which may be
@@ -349,6 +329,16 @@ void __init arm64_memblock_init(void)
 		memblock_remove(0, memstart_addr);
 	}
 
+	/*
+	 * If we are running with a 52-bit kernel VA config on a system that
+	 * does not support it, we have to place the available physical
+	 * memory in the 48-bit addressable part of the linear region, i.e.,
+	 * we have to move it upward. Since memstart_addr represents the
+	 * physical address of PAGE_OFFSET, we have to *subtract* from it.
+	 */
+	if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52))
+		memstart_addr -= _PAGE_OFFSET(48) - _PAGE_OFFSET(52);
+
 	/*
 	 * Apply the memory limit if it was set. Since the kernel may be loaded
 	 * high up in memory, add back the kernel region that must be accessible

drivers/gpio/gpio-mvebu.c

@@ -657,9 +657,8 @@ static void mvebu_pwm_get_state(struct pwm_chip *chip,
 
 	spin_lock_irqsave(&mvpwm->lock, flags);
 
-	val = (unsigned long long)
+	u = readl_relaxed(mvebu_pwmreg_blink_on_duration(mvpwm));
-		readl_relaxed(mvebu_pwmreg_blink_on_duration(mvpwm));
+	val = (unsigned long long) u * NSEC_PER_SEC;
-	val *= NSEC_PER_SEC;
 	do_div(val, mvpwm->clk_rate);
 	if (val > UINT_MAX)
 		state->duty_cycle = UINT_MAX;
@@ -668,21 +667,17 @@ static void mvebu_pwm_get_state(struct pwm_chip *chip,
 	else
 		state->duty_cycle = 1;
 
-	val = (unsigned long long)
+	val = (unsigned long long) u; /* on duration */
-		readl_relaxed(mvebu_pwmreg_blink_off_duration(mvpwm));
+	/* period = on + off duration */
+	val += readl_relaxed(mvebu_pwmreg_blink_off_duration(mvpwm));
 	val *= NSEC_PER_SEC;
 	do_div(val, mvpwm->clk_rate);
-	if (val < state->duty_cycle) {
+	if (val > UINT_MAX)
+		state->period = UINT_MAX;
+	else if (val)
+		state->period = val;
+	else
 		state->period = 1;
-	} else {
-		val -= state->duty_cycle;
-		if (val > UINT_MAX)
-			state->period = UINT_MAX;
-		else if (val)
-			state->period = val;
-		else
-			state->period = 1;
-	}
 
 	regmap_read(mvchip->regs, GPIO_BLINK_EN_OFF + mvchip->offset, &u);
 	if (u)

drivers/hid/wacom_sys.c

@@ -147,9 +147,9 @@ static int wacom_wac_pen_serial_enforce(struct hid_device *hdev,
 	}
 
 	if (flush)
-		wacom_wac_queue_flush(hdev, &wacom_wac->pen_fifo);
+		wacom_wac_queue_flush(hdev, wacom_wac->pen_fifo);
 	else if (insert)
-		wacom_wac_queue_insert(hdev, &wacom_wac->pen_fifo,
+		wacom_wac_queue_insert(hdev, wacom_wac->pen_fifo,
 				       raw_data, report_size);
 
 	return insert && !flush;
@@ -1280,7 +1280,7 @@ static void wacom_devm_kfifo_release(struct device *dev, void *res)
 static int wacom_devm_kfifo_alloc(struct wacom *wacom)
 {
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct kfifo_rec_ptr_2 *pen_fifo = &wacom_wac->pen_fifo;
+	struct kfifo_rec_ptr_2 *pen_fifo;
 	int error;
 
 	pen_fifo = devres_alloc(wacom_devm_kfifo_release,
@@ -1297,6 +1297,7 @@ static int wacom_devm_kfifo_alloc(struct wacom *wacom)
 	}
 
 	devres_add(&wacom->hdev->dev, pen_fifo);
+	wacom_wac->pen_fifo = pen_fifo;
 
 	return 0;
 }

drivers/hid/wacom_wac.h

@@ -342,7 +342,7 @@ struct wacom_wac {
 	struct input_dev *pen_input;
 	struct input_dev *touch_input;
 	struct input_dev *pad_input;
-	struct kfifo_rec_ptr_2 pen_fifo;
+	struct kfifo_rec_ptr_2 *pen_fifo;
 	int pid;
 	int num_contacts_left;
 	u8 bt_features;

drivers/md/dm-integrity.c

@@ -254,6 +254,7 @@ struct dm_integrity_c {
 	bool journal_uptodate;
 	bool just_formatted;
 	bool recalculate_flag;
+	bool legacy_recalculate;
 
 	struct alg_spec internal_hash_alg;
 	struct alg_spec journal_crypt_alg;
@@ -381,6 +382,14 @@ static int dm_integrity_failed(struct dm_integrity_c *ic)
 	return READ_ONCE(ic->failed);
 }
 
+static bool dm_integrity_disable_recalculate(struct dm_integrity_c *ic)
+{
+	if ((ic->internal_hash_alg.key || ic->journal_mac_alg.key) &&
+	    !ic->legacy_recalculate)
+		return true;
+	return false;
+}
+
 static commit_id_t dm_integrity_commit_id(struct dm_integrity_c *ic, unsigned i,
 					  unsigned j, unsigned char seq)
 {
@@ -2998,6 +3007,7 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 		arg_count += !!ic->internal_hash_alg.alg_string;
 		arg_count += !!ic->journal_crypt_alg.alg_string;
 		arg_count += !!ic->journal_mac_alg.alg_string;
+		arg_count += ic->legacy_recalculate;
 		DMEMIT("%s %llu %u %c %u", ic->dev->name, (unsigned long long)ic->start,
 		       ic->tag_size, ic->mode, arg_count);
 		if (ic->meta_dev)
@@ -3017,6 +3027,8 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" sectors_per_bit:%llu", (unsigned long long)ic->sectors_per_block << ic->log2_blocks_per_bitmap_bit);
 			DMEMIT(" bitmap_flush_interval:%u", jiffies_to_msecs(ic->bitmap_flush_interval));
 		}
+		if (ic->legacy_recalculate)
+			DMEMIT(" legacy_recalculate");
 
 #define EMIT_ALG(a, n)							\
 		do {							\
@@ -3625,7 +3637,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	unsigned extra_args;
 	struct dm_arg_set as;
 	static const struct dm_arg _args[] = {
-		{0, 15, "Invalid number of feature args"},
+		{0, 14, "Invalid number of feature args"},
 	};
 	unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec;
 	bool should_write_sb;
@@ -3769,6 +3781,8 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 				goto bad;
 		} else if (!strcmp(opt_string, "recalculate")) {
 			ic->recalculate_flag = true;
+		} else if (!strcmp(opt_string, "legacy_recalculate")) {
+			ic->legacy_recalculate = true;
 		} else {
 			r = -EINVAL;
 			ti->error = "Invalid argument";
@@ -4067,6 +4081,14 @@ try_smaller_buffer:
 		}
 	}
 
+	if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) &&
+	    le64_to_cpu(ic->sb->recalc_sector) < ic->provided_data_sectors &&
+	    dm_integrity_disable_recalculate(ic)) {
+		ti->error = "Recalculating with HMAC is disabled for security reasons - if you really need it, use the argument \"legacy_recalculate\"";
+		r = -EOPNOTSUPP;
+		goto bad;
+	}
+
 	ic->bufio = dm_bufio_client_create(ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev,
 			1U << (SECTOR_SHIFT + ic->log2_buffer_sectors), 1, 0, NULL, NULL);
 	if (IS_ERR(ic->bufio)) {

fs/cifs/smb2pdu.c

@@ -490,8 +490,8 @@ build_preauth_ctxt(struct smb2_preauth_neg_context *pneg_ctxt)
 	pneg_ctxt->ContextType = SMB2_PREAUTH_INTEGRITY_CAPABILITIES;
 	pneg_ctxt->DataLength = cpu_to_le16(38);
 	pneg_ctxt->HashAlgorithmCount = cpu_to_le16(1);
-	pneg_ctxt->SaltLength = cpu_to_le16(SMB311_SALT_SIZE);
+	pneg_ctxt->SaltLength = cpu_to_le16(SMB311_LINUX_CLIENT_SALT_SIZE);
-	get_random_bytes(pneg_ctxt->Salt, SMB311_SALT_SIZE);
+	get_random_bytes(pneg_ctxt->Salt, SMB311_LINUX_CLIENT_SALT_SIZE);
 	pneg_ctxt->HashAlgorithms = SMB2_PREAUTH_INTEGRITY_SHA512;
 }
 
@@ -617,6 +617,9 @@ static void decode_preauth_context(struct smb2_preauth_neg_context *ctxt)
 	if (len < MIN_PREAUTH_CTXT_DATA_LEN) {
 		printk_once(KERN_WARNING "server sent bad preauth context\n");
 		return;
+	} else if (len < MIN_PREAUTH_CTXT_DATA_LEN + le16_to_cpu(ctxt->SaltLength)) {
+		pr_warn_once("server sent invalid SaltLength\n");
+		return;
 	}
 	if (le16_to_cpu(ctxt->HashAlgorithmCount) != 1)
 		printk_once(KERN_WARNING "illegal SMB3 hash algorithm count\n");

fs/cifs/smb2pdu.h

@@ -271,12 +271,20 @@ struct smb2_neg_context {
 	/* Followed by array of data */
 } __packed;
 
-#define SMB311_SALT_SIZE			32
+#define SMB311_LINUX_CLIENT_SALT_SIZE			32
 /* Hash Algorithm Types */
 #define SMB2_PREAUTH_INTEGRITY_SHA512	cpu_to_le16(0x0001)
 #define SMB2_PREAUTH_HASH_SIZE 64
 
-#define MIN_PREAUTH_CTXT_DATA_LEN	(SMB311_SALT_SIZE + 6)
+/*
+ * SaltLength that the server send can be zero, so the only three required
+ * fields (all __le16) end up six bytes total, so the minimum context data len
+ * in the response is six bytes which accounts for
+ *
+ *      HashAlgorithmCount, SaltLength, and 1 HashAlgorithm.
+ */
+#define MIN_PREAUTH_CTXT_DATA_LEN 6
+
 struct smb2_preauth_neg_context {
 	__le16	ContextType; /* 1 */
 	__le16	DataLength;
@@ -284,7 +292,7 @@ struct smb2_preauth_neg_context {
 	__le16	HashAlgorithmCount; /* 1 */
 	__le16	SaltLength;
 	__le16	HashAlgorithms; /* HashAlgorithms[0] since only one defined */
-	__u8	Salt[SMB311_SALT_SIZE];
+	__u8	Salt[SMB311_LINUX_CLIENT_SALT_SIZE];
 } __packed;
 
 /* Encryption Algorithms Ciphers */

fs/ext4/inode.c

@@ -5209,7 +5209,7 @@ static int other_inode_match(struct inode * inode, unsigned long ino,
 	    (inode->i_state & I_DIRTY_TIME)) {
 		struct ext4_inode_info	*ei = EXT4_I(inode);
 
-		inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED);
+		inode->i_state &= ~I_DIRTY_TIME;
 		spin_unlock(&inode->i_lock);
 
 		spin_lock(&ei->i_raw_lock);

fs/fs-writeback.c

@@ -1238,7 +1238,7 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t)
  */
 static int move_expired_inodes(struct list_head *delaying_queue,
 			       struct list_head *dispatch_queue,
-			       int flags, unsigned long dirtied_before)
+			       unsigned long dirtied_before)
 {
 	LIST_HEAD(tmp);
 	struct list_head *pos, *node;
@@ -1254,8 +1254,6 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 		list_move(&inode->i_io_list, &tmp);
 		moved++;
 		spin_lock(&inode->i_lock);
-		if (flags & EXPIRE_DIRTY_ATIME)
-			inode->i_state |= I_DIRTY_TIME_EXPIRED;
 		inode->i_state |= I_SYNC_QUEUED;
 		spin_unlock(&inode->i_lock);
 		if (sb_is_blkdev_sb(inode->i_sb))
@@ -1303,11 +1301,11 @@ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work,
 
 	assert_spin_locked(&wb->list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
-	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, dirtied_before);
+	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before);
 	if (!work->for_sync)
 		time_expire_jif = jiffies - dirtytime_expire_interval * HZ;
 	moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
-				     EXPIRE_DIRTY_ATIME, time_expire_jif);
+				     time_expire_jif);
 	if (moved)
 		wb_io_lists_populated(wb);
 	trace_writeback_queue_io(wb, work, dirtied_before, moved);
@@ -1475,26 +1473,26 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 			ret = err;
 	}
 
+	/*
+	 * If the inode has dirty timestamps and we need to write them, call
+	 * mark_inode_dirty_sync() to notify the filesystem about it and to
+	 * change I_DIRTY_TIME into I_DIRTY_SYNC.
+	 */
+	if ((inode->i_state & I_DIRTY_TIME) &&
+	    (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync ||
+	     time_after(jiffies, inode->dirtied_time_when +
+			dirtytime_expire_interval * HZ))) {
+		trace_writeback_lazytime(inode);
+		mark_inode_dirty_sync(inode);
+	}
+
 	/*
 	 * Some filesystems may redirty the inode during the writeback
 	 * due to delalloc, clear dirty metadata flags right before
 	 * write_inode()
 	 */
 	spin_lock(&inode->i_lock);
-
 	dirty = inode->i_state & I_DIRTY;
-	if (inode->i_state & I_DIRTY_TIME) {
-		if ((dirty & I_DIRTY_INODE) ||
-		    wbc->sync_mode == WB_SYNC_ALL ||
-		    unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) ||
-		    unlikely(time_after(jiffies,
-					(inode->dirtied_time_when +
-					 dirtytime_expire_interval * HZ)))) {
-			dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
-			trace_writeback_lazytime(inode);
-		}
-	} else
-		inode->i_state &= ~I_DIRTY_TIME_EXPIRED;
 	inode->i_state &= ~dirty;
 
 	/*
@@ -1515,8 +1513,6 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 
 	spin_unlock(&inode->i_lock);
 
-	if (dirty & I_DIRTY_TIME)
-		mark_inode_dirty_sync(inode);
 	/* Don't write the inode if only I_DIRTY_PAGES was set */
 	if (dirty & ~I_DIRTY_PAGES) {
 		int err = write_inode(inode, wbc);

fs/io_uring.c

@@ -2226,7 +2226,8 @@ restart:
 		/* Ensure we clear previously set non-block flag */
 		req->rw.ki_flags &= ~IOCB_NOWAIT;
 
-		if (req->fs != current->fs && current->fs != old_fs_struct) {
+		if ((req->fs && req->fs != current->fs) ||
+		    (!req->fs && current->fs != old_fs_struct)) {
 			task_lock(current);
 			if (req->fs)
 				current->fs = req->fs;
@@ -2351,7 +2352,7 @@ out:
 		mmput(cur_mm);
 	}
 	revert_creds(old_cred);
-	if (old_fs_struct) {
+	if (old_fs_struct != current->fs) {
 		task_lock(current);
 		current->fs = old_fs_struct;
 		task_unlock(current);

fs/xfs/libxfs/xfs_trans_inode.c

@@ -100,9 +100,9 @@ xfs_trans_log_inode(
 	 * to log the timestamps, or will clear already cleared fields in the
 	 * worst case.
 	 */
-	if (inode->i_state & (I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED)) {
+	if (inode->i_state & I_DIRTY_TIME) {
 		spin_lock(&inode->i_lock);
-		inode->i_state &= ~(I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED);
+		inode->i_state &= ~I_DIRTY_TIME;
 		spin_unlock(&inode->i_lock);
 	}
 

include/linux/fs.h

@@ -2161,7 +2161,6 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 #define I_DIO_WAKEUP		(1 << __I_DIO_WAKEUP)
 #define I_LINKABLE		(1 << 10)
 #define I_DIRTY_TIME		(1 << 11)
-#define I_DIRTY_TIME_EXPIRED	(1 << 12)
 #define I_WB_SWITCH		(1 << 13)
 #define I_OVL_INUSE		(1 << 14)
 #define I_CREATING		(1 << 15)

include/trace/events/writeback.h

@@ -20,7 +20,6 @@
 		{I_CLEAR,		"I_CLEAR"},		\
 		{I_SYNC,		"I_SYNC"},		\
 		{I_DIRTY_TIME,		"I_DIRTY_TIME"},	\
-		{I_DIRTY_TIME_EXPIRED,	"I_DIRTY_TIME_EXPIRED"}, \
 		{I_REFERENCED,		"I_REFERENCED"}		\
 	)
 

kernel/futex.c

@@ -857,6 +857,29 @@ static struct futex_pi_state *alloc_pi_state(void)
 	return pi_state;
 }
 
+static void pi_state_update_owner(struct futex_pi_state *pi_state,
+				  struct task_struct *new_owner)
+{
+	struct task_struct *old_owner = pi_state->owner;
+
+	lockdep_assert_held(&pi_state->pi_mutex.wait_lock);
+
+	if (old_owner) {
+		raw_spin_lock(&old_owner->pi_lock);
+		WARN_ON(list_empty(&pi_state->list));
+		list_del_init(&pi_state->list);
+		raw_spin_unlock(&old_owner->pi_lock);
+	}
+
+	if (new_owner) {
+		raw_spin_lock(&new_owner->pi_lock);
+		WARN_ON(!list_empty(&pi_state->list));
+		list_add(&pi_state->list, &new_owner->pi_state_list);
+		pi_state->owner = new_owner;
+		raw_spin_unlock(&new_owner->pi_lock);
+	}
+}
+
 static void get_pi_state(struct futex_pi_state *pi_state)
 {
 	WARN_ON_ONCE(!refcount_inc_not_zero(&pi_state->refcount));
@@ -879,17 +902,11 @@ static void put_pi_state(struct futex_pi_state *pi_state)
 	 * and has cleaned up the pi_state already
 	 */
 	if (pi_state->owner) {
-		struct task_struct *owner;
 		unsigned long flags;
 
 		raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags);
-		owner = pi_state->owner;
+		pi_state_update_owner(pi_state, NULL);
-		if (owner) {
+		rt_mutex_proxy_unlock(&pi_state->pi_mutex);
-			raw_spin_lock(&owner->pi_lock);
-			list_del_init(&pi_state->list);
-			raw_spin_unlock(&owner->pi_lock);
-		}
-		rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner);
 		raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags);
 	}
 
@@ -1035,7 +1052,8 @@ static inline void exit_pi_state_list(struct task_struct *curr) { }
  *	FUTEX_OWNER_DIED bit. See [4]
  *
  * [10] There is no transient state which leaves owner and user space
- *	TID out of sync.
+ *	TID out of sync. Except one error case where the kernel is denied
+ *	write access to the user address, see fixup_pi_state_owner().
  *
  *
  * Serialization and lifetime rules:
@@ -1614,26 +1632,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 			ret = -EINVAL;
 	}
 
-	if (ret)
+	if (!ret) {
-		goto out_unlock;
+		/*
-
+		 * This is a point of no return; once we modified the uval
-	/*
+		 * there is no going back and subsequent operations must
-	 * This is a point of no return; once we modify the uval there is no
+		 * not fail.
-	 * going back and subsequent operations must not fail.
+		 */
-	 */
+		pi_state_update_owner(pi_state, new_owner);
-
+		postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
-	raw_spin_lock(&pi_state->owner->pi_lock);
+	}
-	WARN_ON(list_empty(&pi_state->list));
-	list_del_init(&pi_state->list);
-	raw_spin_unlock(&pi_state->owner->pi_lock);
-
-	raw_spin_lock(&new_owner->pi_lock);
-	WARN_ON(!list_empty(&pi_state->list));
-	list_add(&pi_state->list, &new_owner->pi_state_list);
-	pi_state->owner = new_owner;
-	raw_spin_unlock(&new_owner->pi_lock);
-
-	postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
 
 out_unlock:
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
@@ -2456,18 +2463,13 @@ static void unqueue_me_pi(struct futex_q *q)
 	spin_unlock(q->lock_ptr);
 }
 
-static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
+static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-				struct task_struct *argowner)
+				  struct task_struct *argowner)
 {
+	u32 uval, uninitialized_var(curval), newval, newtid;
 	struct futex_pi_state *pi_state = q->pi_state;
-	u32 uval, uninitialized_var(curval), newval;
 	struct task_struct *oldowner, *newowner;
-	u32 newtid;
+	int err = 0;
-	int ret, err = 0;
-
-	lockdep_assert_held(q->lock_ptr);
-
-	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	oldowner = pi_state->owner;
 
@@ -2501,14 +2503,12 @@ retry:
 			 * We raced against a concurrent self; things are
 			 * already fixed up. Nothing to do.
 			 */
-			ret = 0;
+			return 0;
-			goto out_unlock;
 		}
 
 		if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) {
-			/* We got the lock after all, nothing to fix. */
+			/* We got the lock. pi_state is correct. Tell caller. */
-			ret = 0;
+			return 1;
-			goto out_unlock;
 		}
 
 		/*
@@ -2535,8 +2535,7 @@ retry:
 			 * We raced against a concurrent self; things are
 			 * already fixed up. Nothing to do.
 			 */
-			ret = 0;
+			return 1;
-			goto out_unlock;
 		}
 		newowner = argowner;
 	}
@@ -2566,22 +2565,9 @@ retry:
 	 * We fixed up user space. Now we need to fix the pi_state
 	 * itself.
 	 */
-	if (pi_state->owner != NULL) {
+	pi_state_update_owner(pi_state, newowner);
-		raw_spin_lock(&pi_state->owner->pi_lock);
-		WARN_ON(list_empty(&pi_state->list));
-		list_del_init(&pi_state->list);
-		raw_spin_unlock(&pi_state->owner->pi_lock);
-	}
 
-	pi_state->owner = newowner;
+	return argowner == current;
-
-	raw_spin_lock(&newowner->pi_lock);
-	WARN_ON(!list_empty(&pi_state->list));
-	list_add(&pi_state->list, &newowner->pi_state_list);
-	raw_spin_unlock(&newowner->pi_lock);
-	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-
-	return 0;
 
 	/*
 	 * In order to reschedule or handle a page fault, we need to drop the
@@ -2602,17 +2588,16 @@ handle_err:
 
 	switch (err) {
 	case -EFAULT:
-		ret = fault_in_user_writeable(uaddr);
+		err = fault_in_user_writeable(uaddr);
 		break;
 
 	case -EAGAIN:
 		cond_resched();
-		ret = 0;
+		err = 0;
 		break;
 
 	default:
 		WARN_ON_ONCE(1);
-		ret = err;
 		break;
 	}
 
@@ -2622,17 +2607,44 @@ handle_err:
 	/*
 	 * Check if someone else fixed it for us:
 	 */
-	if (pi_state->owner != oldowner) {
+	if (pi_state->owner != oldowner)
-		ret = 0;
+		return argowner == current;
-		goto out_unlock;
-	}
 
-	if (ret)
+	/* Retry if err was -EAGAIN or the fault in succeeded */
-		goto out_unlock;
+	if (!err)
+		goto retry;
 
-	goto retry;
+	/*
+	 * fault_in_user_writeable() failed so user state is immutable. At
+	 * best we can make the kernel state consistent but user state will
+	 * be most likely hosed and any subsequent unlock operation will be
+	 * rejected due to PI futex rule [10].
+	 *
+	 * Ensure that the rtmutex owner is also the pi_state owner despite
+	 * the user space value claiming something different. There is no
+	 * point in unlocking the rtmutex if current is the owner as it
+	 * would need to wait until the next waiter has taken the rtmutex
+	 * to guarantee consistent state. Keep it simple. Userspace asked
+	 * for this wreckaged state.
+	 *
+	 * The rtmutex has an owner - either current or some other
+	 * task. See the EAGAIN loop above.
+	 */
+	pi_state_update_owner(pi_state, rt_mutex_owner(&pi_state->pi_mutex));
 
-out_unlock:
+	return err;
+}
+
+static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
+				struct task_struct *argowner)
+{
+	struct futex_pi_state *pi_state = q->pi_state;
+	int ret;
+
+	lockdep_assert_held(q->lock_ptr);
+
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+	ret = __fixup_pi_state_owner(uaddr, q, argowner);
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	return ret;
 }
@@ -2656,8 +2668,6 @@ static long futex_wait_restart(struct restart_block *restart);
  */
 static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 {
-	int ret = 0;
-
 	if (locked) {
 		/*
 		 * Got the lock. We might not be the anticipated owner if we
@@ -2668,8 +2678,8 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		 * stable state, anything else needs more attention.
 		 */
 		if (q->pi_state->owner != current)
-			ret = fixup_pi_state_owner(uaddr, q, current);
+			return fixup_pi_state_owner(uaddr, q, current);
-		goto out;
+		return 1;
 	}
 
 	/*
@@ -2680,24 +2690,17 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 	 * Another speculative read; pi_state->owner == current is unstable
 	 * but needs our attention.
 	 */
-	if (q->pi_state->owner == current) {
+	if (q->pi_state->owner == current)
-		ret = fixup_pi_state_owner(uaddr, q, NULL);
+		return fixup_pi_state_owner(uaddr, q, NULL);
-		goto out;
-	}
 
 	/*
 	 * Paranoia check. If we did not take the lock, then we should not be
-	 * the owner of the rt_mutex.
+	 * the owner of the rt_mutex. Warn and establish consistent state.
 	 */
-	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) {
+	if (WARN_ON_ONCE(rt_mutex_owner(&q->pi_state->pi_mutex) == current))
-		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
+		return fixup_pi_state_owner(uaddr, q, current);
-				"pi-state %p\n", ret,
-				q->pi_state->pi_mutex.owner,
-				q->pi_state->owner);
-	}
 
-out:
+	return 0;
-	return ret ? ret : locked;
 }
 
 /**
@@ -2909,7 +2912,6 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 			 ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to;
-	struct futex_pi_state *pi_state = NULL;
 	struct task_struct *exiting = NULL;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
@@ -3046,23 +3048,9 @@ no_block:
 	if (res)
 		ret = (res < 0) ? res : 0;
 
-	/*
-	 * If fixup_owner() faulted and was unable to handle the fault, unlock
-	 * it and return the fault to userspace.
-	 */
-	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) {
-		pi_state = q.pi_state;
-		get_pi_state(pi_state);
-	}
-
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
 
-	if (pi_state) {
-		rt_mutex_futex_unlock(&pi_state->pi_mutex);
-		put_pi_state(pi_state);
-	}
-
 	goto out_put_key;
 
 out_unlock_put_key:
@@ -3328,7 +3316,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 				 u32 __user *uaddr2)
 {
 	struct hrtimer_sleeper timeout, *to;
-	struct futex_pi_state *pi_state = NULL;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
 	union futex_key key2 = FUTEX_KEY_INIT;
@@ -3406,16 +3393,17 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
-			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
-				pi_state = q.pi_state;
-				get_pi_state(pi_state);
-			}
 			/*
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
 			 */
 			put_pi_state(q.pi_state);
 			spin_unlock(q.lock_ptr);
+			/*
+			 * Adjust the return value. It's either -EFAULT or
+			 * success (1) but the caller expects 0 for success.
+			 */
+			ret = ret < 0 ? ret : 0;
 		}
 	} else {
 		struct rt_mutex *pi_mutex;
@@ -3446,25 +3434,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (res)
 			ret = (res < 0) ? res : 0;
 
-		/*
-		 * If fixup_pi_state_owner() faulted and was unable to handle
-		 * the fault, unlock the rt_mutex and return the fault to
-		 * userspace.
-		 */
-		if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
-			pi_state = q.pi_state;
-			get_pi_state(pi_state);
-		}
-
 		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
 	}
 
-	if (pi_state) {
-		rt_mutex_futex_unlock(&pi_state->pi_mutex);
-		put_pi_state(pi_state);
-	}
-
 	if (ret == -EINTR) {
 		/*
 		 * We've already been requeued, but cannot restart by calling

kernel/locking/rtmutex.c

@@ -1718,8 +1718,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
  * possible because it belongs to the pi_state which is about to be freed
  * and it is not longer visible to other tasks.
  */
-void rt_mutex_proxy_unlock(struct rt_mutex *lock,
+void rt_mutex_proxy_unlock(struct rt_mutex *lock)
-			   struct task_struct *proxy_owner)
 {
 	debug_rt_mutex_proxy_unlock(lock);
 	rt_mutex_set_owner(lock, NULL);

kernel/locking/rtmutex_common.h

@@ -133,8 +133,7 @@ enum rtmutex_chainwalk {
 extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
 extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				       struct task_struct *proxy_owner);
-extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
+extern void rt_mutex_proxy_unlock(struct rt_mutex *lock);
-				  struct task_struct *proxy_owner);
 extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
 extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,

kernel/trace/ring_buffer.c

@@ -4448,6 +4448,8 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
+	/* prevent another thread from changing buffer sizes */
+	mutex_lock(&buffer->mutex);
 
 	atomic_inc(&buffer->resize_disabled);
 	atomic_inc(&cpu_buffer->record_disabled);
@@ -4471,6 +4473,8 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 
 	atomic_dec(&cpu_buffer->record_disabled);
 	atomic_dec(&buffer->resize_disabled);
+
+	mutex_unlock(&buffer->mutex);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 

mm/slub.c

@@ -5819,10 +5819,8 @@ static int sysfs_slab_add(struct kmem_cache *s)
 
 	s->kobj.kset = kset;
 	err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
-	if (err) {
+	if (err)
-		kobject_put(&s->kobj);
 		goto out;
-	}
 
 	err = sysfs_create_group(&s->kobj, &slab_attr_group);
 	if (err)

tools/build/Makefile

@@ -15,10 +15,6 @@ endef
 $(call allow-override,CC,$(CROSS_COMPILE)gcc)
 $(call allow-override,LD,$(CROSS_COMPILE)ld)
 
-HOSTCC ?= gcc
-HOSTLD ?= ld
-HOSTAR ?= ar
-
 export HOSTCC HOSTLD HOSTAR
 
 ifeq ($(V),1)

tools/objtool/Makefile

@@ -3,15 +3,6 @@ include ../scripts/Makefile.include
 include ../scripts/Makefile.arch
 
 # always use the host compiler
-ifneq ($(LLVM),)
-HOSTAR	?= llvm-ar
-HOSTCC	?= clang
-HOSTLD	?= ld.lld
-else
-HOSTAR	?= ar
-HOSTCC	?= gcc
-HOSTLD	?= ld
-endif
 AR	 = $(HOSTAR)
 CC	 = $(HOSTCC)
 LD	 = $(HOSTLD)

tools/perf/Makefile.perf

@@ -163,10 +163,6 @@ endef
 
 LD += $(EXTRA_LDFLAGS)
 
-HOSTCC  ?= gcc
-HOSTLD  ?= ld
-HOSTAR  ?= ar
-
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 LLVM_CONFIG ?= llvm-config
 

tools/power/acpi/Makefile.config

@@ -54,7 +54,6 @@ INSTALL_SCRIPT = ${INSTALL_PROGRAM}
 CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc-
 CROSS_COMPILE ?= $(CROSS)
 LD = $(CC)
-HOSTCC = gcc
 
 # check if compiler option is supported
 cc-supports = ${shell if $(CC) ${1} -S -o /dev/null -x c /dev/null > /dev/null 2>&1; then echo "$(1)"; fi;}

tools/scripts/Makefile.include

@@ -59,6 +59,16 @@ $(call allow-override,LD,$(CROSS_COMPILE)ld)
 $(call allow-override,CXX,$(CROSS_COMPILE)g++)
 $(call allow-override,STRIP,$(CROSS_COMPILE)strip)
 
+ifneq ($(LLVM),)
+HOSTAR  ?= llvm-ar
+HOSTCC  ?= clang
+HOSTLD  ?= ld.lld
+else
+HOSTAR  ?= ar
+HOSTCC  ?= gcc
+HOSTLD  ?= ld
+endif
+
 ifeq ($(CC_NO_CLANG), 1)
 EXTRA_WARNINGS += -Wstrict-aliasing=3
 endif